Audio Augmentation for Non-Native Children's Speech Recognition through Discriminative Learning.
Kodali RadhaMohan BansalPublished in: Entropy (2022)
Keyphrases
- discriminative learning
- speech recognition
- speech recognition technology
- speaker identification
- generative model
- language model
- pattern recognition
- hidden markov models
- automatic speech recognition
- speech synthesis
- maximum margin
- students with learning disabilities
- speech signal
- highly efficient
- structured prediction
- weakly supervised
- pairwise constraints
- audio visual speech recognition
- image set
- broadcast news
- signal processing